© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3050
    Prev
    Next
    INDEX
    Explanations

    creative works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.88
    Билгалдахарш
    -0.82
    Personensuche
    -0.80
     الرياضيه
    -0.75
    kháu
    -0.73
     Wicidata
    -0.71
    +#+
    -0.70
     Normdatei
    -0.69
    ########.
    -0.68
    tinyos
    -0.68
    POSITIVE LOGITS
     consists
    0.60
     consist
    0.57
     starts
    0.47
     is
    0.47
     begins
    0.46
     includes
    0.44
     comprises
    0.42
    TypedDataSet
    0.41
    хема
    0.40
    keyboardType
    0.40
    Activations Density 0.004%

    No Known Activations